{"id":"W2009853003","doi":"10.1038/nmeth.2762","title":"Refined DNase-seq protocol and data analysis reveals intrinsic bias in transcription factor footprint identification","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":225,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Human Genome Research Institute","keywords":"Transcription factor; Biology; DNase I hypersensitive site; Hypersensitive site; Deoxyribonuclease I; Cleavage (geology); Transcription (linguistics); DNA footprinting; Computational biology; Genetics; DNA binding site; DNA; Gene; DNA-binding protein; Promoter; Base sequence; Gene expression","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009188297,0.0001388231,0.0002029207,0.0001392763,0.00003670201,0.00007041014,0.0003034835,0.0003635734,0.00002025878],"category_scores_gemma":[0.0003205251,0.0001236972,0.00005937664,0.0003024606,0.0000257835,0.000008167992,0.0001412593,0.0002359308,0.000001746553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000021625,"about_ca_system_score_gemma":0.00002642347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004851421,"about_ca_topic_score_gemma":0.0001888638,"domain_scores_codex":[0.9985955,0.0003081565,0.0003368539,0.0005144777,0.00009296592,0.0001519851],"domain_scores_gemma":[0.9988456,0.00002759777,0.0001418299,0.0008463996,0.00008317285,0.00005544976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002192759,0.00003771434,0.004629588,0.0000449189,0.00009656012,3.645006e-7,0.00003116228,0.00002178149,0.9223987,0.00007812863,0.0000853288,0.07255381],"study_design_scores_gemma":[0.001062719,0.0001073238,0.8008301,0.00001884317,0.0001693036,0.000005791835,0.00006105454,0.008991341,0.1721589,0.002141688,0.01402028,0.0004326247],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9508131,0.0001998979,0.03906904,0.0002706869,0.00008748831,0.009401848,0.00005842548,0.00001218595,0.00008732682],"genre_scores_gemma":[0.8554061,0.0000380315,0.1394736,0.000110563,0.00007122084,0.004122945,0.0005454711,0.00001829803,0.0002137312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7962005,"threshold_uncertainty_score":0.5044226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04832277110834026,"score_gpt":0.395162842891399,"score_spread":0.3468400717830587,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}